# Super-resolution PET imaging using convolutional neural networks

arXiv: https://arxiv.org/abs/1906.03645 · HTML: https://mlsanity.com/paper/1906.03645/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2019.

## Built on by (most cited first, 6 of 6)

- [QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noise](https://mlsanity.com/paper/2208.14839/) (2022)
- [No-Clean-Reference Image Super-Resolution: Application to Electron Microscopy](https://mlsanity.com/paper/2401.08115/) (2024)
- [CNNs and GANs in MRI-based cross-modality medical image estimation](https://mlsanity.com/paper/2106.02198/) (2021)
- [Estimating Uncertainty in PET Image Reconstruction via Deep Posterior Sampling](https://mlsanity.com/paper/2306.04664/) (2023)
- [Enhance the Image: Super Resolution using Artificial Intelligence in MRI](https://mlsanity.com/paper/2406.13625/) (2024)
- [Variable Resolution Sampling and Deep Learning Image Recovery for Accelerated Multi-Spectral MRI Near Metal Implants](https://mlsanity.com/paper/2410.23329/) (2024)

## Abstract (arXiv)

Positron emission tomography (PET) suffers from severe resolution limitations which limit its quantitative accuracy. In this paper, we present a super-resolution (SR) imaging technique for PET based on convolutional neural networks (CNNs). To facilitate the resolution recovery process, we incorporate high-resolution (HR) anatomical information based on magnetic resonance (MR) imaging. We introduce the spatial location information of the input image patches as additional CNN inputs to accommodate the spatially-variant nature of the blur kernels in PET. We compared the performance of shallow (3-layer) and very deep (20-layer) CNNs with various combinations of the following inputs: low-resolution (LR) PET, radial locations, axial locations, and HR MR. To validate the CNN architectures, we performed both realistic simulation studies using the BrainWeb digital phantom and clinical neuroimaging data analysis. For both simulation and clinical studies, the LR PET images were based on the Siemens HR+ scanner. Two different scenarios were examined in simulation: one where the target HR image is the ground-truth phantom image and another where the target HR image is based on the Siemens HRRT scanner --- a high-resolution dedicated brain PET scanner. The latter scenario was also examined using clinical neuroimaging datasets. A number of factors affected relative performance of the different CNN designs examined, including network depth, target image quality, and the resemblance between the target and anatomical images. In general, however, all CNNs outperformed classical penalized deconvolution techniques by large margins both qualitatively (e.g., edge and contrast recovery) and quantitatively (as indicated by two metrics: peak signal-to-noise-ratio and structural similarity index).